Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    proper nouns and names with multiple parts, including some indications it might be trying to extract politicians as well.

    oai_token-act-pair · gemini-2.0-flash

    Defaultib

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    <bos>
    -0.66
    je
    -0.47
     R
    -0.44
     S
    -0.44
    titution
    -0.43
    ate
    -0.43
    Koordinaten
    -0.43
    l
    -0.41
    <eos>
    -0.40
    ть
    -0.40
    POSITIVE LOGITS
     Theſe
    0.83
     ujednoznacz
    0.77
     المعيارى
    0.76
     Efq
    0.75
    AddTagHelper
    0.75
    expandindo
    0.73
     purpoſe
    0.72
     myſelf
    0.72
     ddelweddau
    0.71
     Monfieur
    0.71
    Act Density 1.353%

    No Known Activations